Assistant Command Disambiguation With Passive Pivoting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated assistants often misinterpret ambiguous user inputs, leading to prolonged dialogs and wastage of computational resources as users are required to clarify their commands, especially when multiple applications or media items with similar names are involved.

Innovation Solution

An automated assistant that passively disambiguates spoken utterances by automatically initializing the most likely operation while providing selectable elements for alternative interpretations, allowing users to pivot quickly without additional input.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If the automated assistant automatically selects a particular application or media content item in response to an ambiguous user input, then the response speed is improved, but the accuracy of fulfilling user intent deteriorates

Engineering Contradiction:
Improveresponse speedVSAvoidaccuracy of fulfilling user intent
Core Design Contradiction:
SpeedVSMeasurement precision

Solution Approach 1:

The system performs preliminary actions by automatically selecting and initializing the most likely interpretation while simultaneously preparing alternative interpretations in the background. This allows the system to respond immediately to the user while having alternative operations ready to execute if the user selects different selectable elements, thus achieving both fast response and accurate intent fulfillment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts between automatic selection and user choice by initially executing the most likely interpretation while providing selectable elements for alternative interpretations. The system can pivot from automatic execution to user-selected execution based on real-time user input, making the system adaptable to both fast-response and high-accuracy scenarios.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If the automated assistant requires user clarification for ambiguous inputs, then the accuracy of fulfilling user intent is improved, but the dialog duration increases

Engineering Contradiction:
Improveaccuracy of fulfilling user intentVSAvoiddialog duration
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically selecting and initializing the most likely interpretation while simultaneously preparing alternative interpretations in the background. This allows the system to respond immediately to the user while having alternative operations ready to execute if the user selects different selectable elements, thus achieving both fast response and accurate intent fulfillment.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If the automated assistant provides multiple selectable options for ambiguous inputs, then the accuracy of fulfilling user intent is improved, but the device complexity increases

Engineering Contradiction:
Improveaccuracy of fulfilling user intentVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts only the necessary alternative interpretations that have significant probability of being the user's intent, rather than presenting all possible interpretations. This reduces the number of selectable elements presented to the user, simplifying the interface while still providing accurate disambiguation options when needed.

Inventive Principle:
Principle #2Taking out (Extraction)

4Measurement precision

If the automated assistant waits for user confirmation before executing commands, then the accuracy of fulfilling user intent is improved, but the productivity decreases

Engineering Contradiction:
Improveaccuracy of fulfilling user intentVSAvoidcommand fulfillment efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary actions by automatically selecting and initializing the most likely interpretation while simultaneously preparing alternative interpretations in the background. This allows the system to respond immediately to the user while having alternative operations ready to execute if the user selects different selectable elements, thus achieving both fast response and accurate intent fulfillment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts between automatic selection and user choice by initially executing the most likely interpretation while providing selectable elements for alternative interpretations. The system can pivot from automatic execution to user-selected execution based on real-time user input, making the system adaptable to both fast-response and high-accuracy scenarios.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4133481B1Passive disambiguation of assistant commands
Publication Date: 2026.03.11 GOOGLE LLC
  • EP4133481B1 patent drawingFigure 1A
  • EP4133481B1 patent drawingFigure 1B
  • EP4133481B1 patent drawingFigure 1C

AI summary

Implementations set forth herein relate to an automated assistant that can initialize execution of an assistant command associated with an interpretation that is predicted to be responsive to a user input, while simultaneously providing suggestions for alternative assistant command(s) associated with alternative interpretation(s) that is/are also predicted to be responsive to the user input. The alternative assistant command(s) that are suggested can be selectable such that, when selected, the automated assistant can pivot from executing the assistant command to initializing execution of the selected alternative assistant command(s). Further, the alternative assistant command(s) that are suggested can be partially fulfilled prior to any user selection thereof. Accordingly, implementations set forth herein can enable the automated assistant to quickly and efficiently pivot between assistant commands that are predicted to be responsive to the user input.